An Approach for Efficient Classification of CT Scan Brain Haemorrhage Types Using GLCM Features with Multilayer Perceptron

Author(s):  
A. Aafreen Nawresh ◽  
S. Sasikala
1991 ◽  
Vol 49 (3) ◽  
pp. 251-254 ◽  
Author(s):  
Walter Oleschko Arruda

The objective of this study was to establish the etiology of epilepsy in 210 chronic epileptics (110 female, 100 male), aged 14-82 years (34.2±13.3). Patients less than 10 years-old and alcoholism were excluded. All underwent neurological examination, routine blood tests, EEG and CT-scan. Twenty patients (10.5%) were submitted to spinal tap for CSF examination. Neurological examination was abnormal in 26 (12.4%), the EEG in 68 (45.5%), and CT-scan in 93 (44.3%). According to the International Classification of Epileptic Seizures (1981), 101 (48.1%) have generalized seizures, 66 (31.4%) partial seizures secondarily generalized, 25 (11.8%) simple partial and complex partial seizures, and 14 (6.6%) generalized and partial seizures. Four patients (2.0%) could not be classified. In 125 (59.5%) patients the etiology was unknown. Neurocysticercosis accounted for 57 (27.1%) of cases, followed by cerebrovascular disease 8 (3.8%), perinatal damage 5 (2.4%), familial epilepsy 4 (1.9%), head injury 4 (1.9%), infective 1 (0.5%), and miscelanea 6 (2.8%).


2016 ◽  
Vol 19 (1) ◽  
pp. 49-59 ◽  
Author(s):  
Nina Pavlin-Bernardić ◽  
◽  
Silvija Ravić ◽  
Ivan Pavao Matić ◽  
◽  
...  

Artificial neural networks have a wide use in the prediction and classification of different variables, but their application in the area of educational psychology is still relatively rare. The aim of this study was to examine the accuracy of artificial neural networks in predicting students’ general giftedness. The participants were 221 fourth grade students from one Croatian elementary school. The input variables for artificial neural networks were teachers’ and peers’ nominations, school grades, earlier school readiness assessment and parents’ education. The output variable was the result on the Standard Progressive Matrices (Raven, 1994), according to which students were classified as gifted or non-gifted. We tested two artificial neural networks’ algorithms: multilayer perceptron and radial basis function. Within each algorithm, a number of different types of activation functions were tested. 80% of the sample was used for training the network and the remaining 20% to test the network. For a criterion according to which students were classified as gifted if their result on the Standard Progressive Matrices was in the 95th centile or above, the best model was obtained by the hyperbolic tangent multilayer perceptron, which had a high accuracy of 100% of correctly classified non-gifted students and 75% correctly classified gifted students in the test sample. When the criterion was the 90th centile or above, the best model was also obtained by the hyperbolic tangent multilayer perceptron, but the accuracy was lower: 94.7% in the classification of non-gifted students and 66.7% in the classification of gifted students. The study has shown artificial neural networks’ potential in this area, which should be further explored. Keywords: gifted students, identification of gifted students, artificial neural networks


Author(s):  
K. S. Raja Rajeswari ◽  
R. Niranjana

Background: Eclampsia is a leading cause of maternal death, with classical neurological symptoms that include headache, nausea, vomiting, cortical blindness, coma and convulsions. Computed tomography (CT) scan helps in diagnosing and management of eclampsia in pregnant women. The present study was done with the objective to analyse the findings of CT scan of brain in eclampsia, to identify the prevalence of neurovascular complications in these cases and to determine if these findings can be of value in determining the prognosis of this disorder.Methods: This was a prospective study done on 100 patients with eclampsia. All of the 100 patients were screened with CT scan brain at Institute of Obstetrics and Gynaecology, Egmore, Chennai during the period from August 2008 to August 2009. All the data were analyzed and compared between the groups of positive CT scan and negative CT scan observations.Results: Out of 100 patients, positive CT scan findings were noticed in 15 patients. Of them, 7 patients expired, and 8 patients survived after treatment. Of the expired patients (7), 5 of them expired due to brain haemorrhage, and 1 patient died with cerebral oedema and 1 with brain infarction. Cerebral odema (46%) was the most common positive CT finding.  Parietal region of brain was the most common (40%) affected area.Conclusions: CT scan of brain provides valuable information in determining the prognosis and the prevalence of neurovascular complications in Eclampsia.


Author(s):  
Abdulkadir Özdemir ◽  
Uğur Yavuz ◽  
Fares Abdulhafidh Dael

<span>Nowadays data mining become one of the technologies that paly major effect on business intelligence. However, to be able to use the data mining outcome the user should go through many process such as classified data. Classification of data is processing data and organize them in specific categorize to be use in most effective and efficient use. In data mining one technique is not applicable to be applied to all the datasets. This paper showing the difference result of applying different techniques on the same data. This paper evaluates the performance of different classification techniques using different datasets. In this study four data classification techniques have chosen. They are as follow, BayesNet, NaiveBayes, Multilayer perceptron and J48. The selected data classification techniques performance tested under two parameters, the time taken to build the model of the dataset and the percentage of accuracy to classify the dataset in the correct classification. The experiments are carried out using Weka 3.8 software. The results in the paper demonstrate that the efficiency of Multilayer Perceptron classifier in overall the best accuracy performance to classify the instances, and NaiveBayes classifiers were the worst outcome of accuracy to classifying the instance for each dataset.</span>


2021 ◽  
Vol 12 (4) ◽  
pp. 177-200
Author(s):  
Soumen Mukherjee ◽  
Arunabha Adhikari ◽  
Madhusudan Roy

This paper represents a scheme of melanoma detection using handcrafted feature set with meta-heuristically optimized multilayer perceptron (MLP) parameters. Features including shape, color, and texture are extracted from camera images of skin lesion collected from University of Waterloo database. The features are used in two different ways for binary classification of the data into benign and malignant class. 1) The extracted features are ranked on their relevance using ReleifF ranking algorithm and also converted into PCA components and ranked according to their variance. Best result is obtained with 50 best ranked raw features with accuracy of 87.1%. 2) All 1,888 features are fed to an MLP with two hidden layers, with number of neurons optimized by two different metaheuristic algorithms, namely particle swarm optimization (PSO) and simulated annealing (SA) separately. The latter method is found to be more efficient, and an accuracy of 88.38%, sensitivity of 92.22%, and specificity of 83.07% are achieved by PSO, which is better in comparison with the latest research on this dataset.


Sign in / Sign up

Export Citation Format

Share Document